1 Camada 1 · Agregação
Sinais de quatro fontes: clássico, fator, ML, hipótese IA.
Bring classic strategies, factors, ML models, and AI-assisted hypotheses into an inspectable candidate set. Candidate generation does not establish validity.
AI-Native Quant Research
StratCraft
Move from hypothesis to data, candidates, experiments, reproducible evidence, and the next research decision.
AI guides the workflow. You remain in control.
AI-Native Quant Research · human-controlled
Research evidence · evaluation and transparent baselines
Illustrative interface, not a performance claim500–1000×
workload-specific benchmarks
2000+/sess
reviewed candidates
7
fornecedores LLM
1000+
governed research set
Research Capabilities in Context
Product maturity is measured by evidence and governed decisions, not candidate volume.
0
AI helps frame, build, and explain research
0
Users approve operations and next decisions
0
Community execution, Artifacts, evidence, and lineage
0
Community, hosted inference, and Commercial boundaries
The Research Capability Chain
AI connects research work while the user controls operations and decisions.
2 Camada 2 · Velocidade
Local C++23 execution, with workload-specific evidence.
Run approved backtests locally and preserve inputs, Artifacts, lineage, and results. Performance claims remain benchmark-specific.
Python
(vectorbt)1×
(vectorbt)1×
Rust
(NautilusTrader)42×
(NautilusTrader)42×
StratCraft
C++23784×
C++23784×
3 Camada 3 · Composição
Transparent evaluation. Governance before promotion.
Compare candidates against appropriate baselines and retain acceptance or rejection evidence. Advanced fusion remains separately admitted.
∞ Tudo local · sem dependência
Tudo local, sem lock-in
Community AI Studio supports loginless direct BYOK or a supported local model. Optional hosted inference is a separate, disclosed boundary.
Windows
macOS
Linux
Why Research Continuity Matters
Connected evidence and decisions matter more than generating a larger candidate count.
Abordagem convencional
StratCraft Research Workflow
Origem dos sinais
Criar manualmente 3-5 estratégias
pages.quantnexus.scaleComparison.row1Quantnexus
Throughput de backtest
Disconnected tools and incomplete run context
pages.quantnexus.scaleComparison.row2Quantnexus
Composição de portfólio
Escolher a melhor estratégia e operá-la sozinha
pages.quantnexus.scaleComparison.row3Quantnexus
Abordagem estrutural
Risco de concentração. Uma estratégia falha, tudo falha
pages.quantnexus.scaleComparison.row4Quantnexus
A larger search space creates more opportunities for false discoveries. StratCraft treats evidence, rejection, and research memory as first-class product responsibilities.
O pipeline de 3 camadas
1
Camada 1: Agregar de quatro fontes
Reúna estratégias clássicas (bibliotecas de código aberto, sistemas publicados, TradingView, as suas próprias), fatores quant, modelos de ML e hipóteses geradas por LLM. Uma ideia torna-se uma população de candidatos, não uma única estratégia codificada à mão.
2
Camada 2: Backtest de toda a fábrica
The local C++23 engine runs approved backtests and retains inspectable results. Named data routes and performance evidence are stated per workload.
3
Camada 3: Compor e compor
Compare surviving candidates with transparent baselines. Community includes equal-weight combination and replay; advanced fusion and decision policies are separately admitted.
Aprofundar
Research Modules, One Connected Workflow
Cada módulo do pipeline de 3 camadas. Desde a agregação de quatro fontes até à execução C++23 e composição estatística.
Explorar →Porque a velocidade C++23 importa em escala
Architecture evolution, workload-specific benchmark evidence, and local execution boundaries.
Explorar →Inicie a sua fábrica de sinais
O nível gratuito inclui o motor de backtest C++, deteção de regime e dados YFinance + Dukascopy: tudo o que precisa para começar a construir em escala.